Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Turning Claude Code into my best design partner

betweentheprompts.com

Post reply on HN
Print view View original

31–40 of 87 posts

Re: Turning Claude Code into my best design partner

#31

Post by a_bonobo »

hetspookjee wrote: post #6

Over the last 2 weeks (evenings only) I've spend a lot of time crafting the "perfect prompt" for claude code to one shot the project. I ended up with a rather small CLAUDE.md file that references 8 other MD files, ranging from project_architecture, models_spec, build_sequence, test_hierarchy, test_scenarios, and some other files. It is a project for model based governance of Databricks Unity Catalog, with which I do…

I feel we're developing something like what made Test-Driven Development so strong: TTD forced you to sit down and design your system first, rather than making it all up on the fly. In the past we mapped the system while we were building the code for it.

This kind of AI-driven development feels very similar to that. By forcing you to sit down and map the territory you're planning to build in, the coding itself becomes secondary, just boilerplate to implement the design decision you've made. And AI is great at boilerplate!

Re: Turning Claude Code into my best design partner

#33

Post by brainless »

hetspookjee wrote: post #6

Over the last 2 weeks (evenings only) I've spend a lot of time crafting the "perfect prompt" for claude code to one shot the project. I ended up with a rather small CLAUDE.md file that references 8 other MD files, ranging from project_architecture, models_spec, build_sequence, test_hierarchy, test_scenarios, and some other files. It is a project for model based governance of Databricks Unity Catalog, with which I do…

These days, I record product details, user journey, etc. with voice, and kick off the product technical details documentation process. Minimal CLAUDE.md. GitHub based workflow for software development process. I am struggling with generating good CI workflows, on it.

Here is my playbook: https://nocodo.com/playbook/

Re: Turning Claude Code into my best design partner

#34

Post by hetspookjee »

a_bonobo wrote: post #31
hetspookjee wrote: post #6

Over the last 2 weeks (evenings only) I've spend a lot of time crafting the "perfect prompt" for claude code to one shot the project. I ended up with a rather small CLAUDE.md file that references 8 other MD files, ranging from project_architecture, models_spec, build_sequence, test_hierarchy, test_scenarios, and some other files. It is a project for model based governance of Databricks Unity Catalog, with which I do…

I feel we're developing something like what made Test-Driven Development so strong: TTD forced you to sit down and design your system first, rather than making it all up on the fly. In the past we mapped the system while we were building the code for it. This kind of AI-driven development feels very similar to that. By forcing you to sit down and map the territory you're planning to build in, the coding itself become…

That is exactly what this felt like indeed! I found a lot of interest in both refining the test strategy and test decisions, but when it started implementing some core functions were in fact lost in the process. This rather leaky memory still suprises me every now and then. Especially 'undoing' things is a big challenge as the (do not) kind of route versus the (do) route is so much more confusing for the LLM, it seems.

Re: Turning Claude Code into my best design partner

#37

Post by fuckaj »

dustingetz wrote: post #25
Crowberry wrote: post #3

I’ve recently tried out Claude Code for a bit, I’ll make sure to give the suggested approach a go! It sounds like a nice workflow. But I’m negatively surprised with the amount of money CC costs. Just a simple refactoring cost me about 5min + 15min review and 4usd, had I done it myself it might have taken 15-20min as well. How much money do you typically spend on features using CC? Nobody seems to mention this

the investor bull case in AI is to cannabalize the labor markets at 15% margin, so 1:1 labor:AI budget is where we are headed next - e.g. $100k/100k for a senior dev. The AI share will come out of dev budgets, so expect senior salaries to fall and team sizes to shrink by a lot if this stuff works. Remember we’re in the land grab phase, all subsidized by VCs, but we’re speed running through the stages as and this phas…

What if once the 100k dev jobs are gone the equivalent value in terms of AI is nowhere near that. Say it is 5k instead?

Due to oversupply. First you needed humans who can code. But now you need scalable compute.

Equivalent would be hiring those people to wave a flag infront of a car. They are replaced bt modern cars, but you dont get to receive the flag wavers wage as captured value for long if at all.

Re: Turning Claude Code into my best design partner

#38

Post by mattmanser »

a_bonobo wrote: post #31
hetspookjee wrote: post #6

Over the last 2 weeks (evenings only) I've spend a lot of time crafting the "perfect prompt" for claude code to one shot the project. I ended up with a rather small CLAUDE.md file that references 8 other MD files, ranging from project_architecture, models_spec, build_sequence, test_hierarchy, test_scenarios, and some other files. It is a project for model based governance of Databricks Unity Catalog, with which I do…

I feel we're developing something like what made Test-Driven Development so strong: TTD forced you to sit down and design your system first, rather than making it all up on the fly. In the past we mapped the system while we were building the code for it. This kind of AI-driven development feels very similar to that. By forcing you to sit down and map the territory you're planning to build in, the coding itself become…

I feel TDD ended up fizzling out quite a bit in the industry, with some evangelists later admitting they'd taken to often writing the code first, then the tests.

To me it's always felt like waterfall in disguise and just didn't fit how I make programs. I feel it's just not a good way to build a complex system with unknown unknowns.

That the AI design process seems to rely on this same pattern feels off to me, and shows a weakness of developing this way.

It might not matter, admittedly. It could be that the flexibility of having the AI rearchitect a significant chunk of code on the fly works as a replacement to the flexibility of designing as you go.

Re: Turning Claude Code into my best design partner

#39

Post by zuInnp »

What I don't get about all the "if you plan it out first, it gets better" approach is, how did they work before?!

For anything bigger than small size features, I always think about what I do and why I do things. Sometimes in my head, sometimes on paper, a Confluence page or a white board.

I don't really get it. 80 % of software engineering is to figure out what you need and how to achieve this. You check with the stake holders, write down the idea of what you want to do and WHY you want to do it. You do some research.

Last 20 % of the process is coding.

This was always the process. You don't need AI for proper planning and defining your goals.

Re: Turning Claude Code into my best design partner

#40

Post by samrus »

interesting. that living plan document is something humans learn to make and update themselves. these problems are dynamical, requiring the solver to maintain state, and the plan is what records that.

doing it for the LLM really highlights that limitation. they arent trained statefully, not at the foundation model, where it matters. that state gets reproduced on top of the model in the form of "reasoning" and "chain of thought" but that level of scaffolding is a classic example of the bitter lesson. like semantic trees of old.

the representation learning + transformer model needs to be evolved to handle state, then it should be able to do these things itself

Post reply on HN